has_columns decorator

.gitignore

@@ -69,3 +69,10 @@ wheelhouse/
 *.zip
 *.csv
 
+# Pycharm files
+.idea
+.idea/droste-engarde.iml
+.idea/misc.xml
+.idea/modules.xml
+.idea/workspace.xml
+.idea/vcs.xml

README.md

@@ -68,4 +68,4 @@ See Also
 ========
 
 - [assertr](https://github.com/tonyfischetti/assertr)
-- [Validada](https://github.com/jnmclarty/validada)
+- [Validada](https://github.com/jnmclarty/validada)

engarde/checks.py

@@ -42,6 +42,7 @@ def none_missing(df, columns=None):
         raise
     return df
 
+
 def is_monotonic(df, items=None, increasing=None, strict=False):
     """
     Asserts that the DataFrame is monotonic.
@@ -68,7 +69,7 @@ def is_monotonic(df, items=None, increasing=None, strict=False):
         if increasing:
             good = getattr(s, 'is_monotonic_increasing')
         elif increasing is None:
-            good = getattr(s, 'is_monotonic') | getattr(s, 'is_monotonic_decreasing')
+            good = getattr(s, 'is_monotonic') | getattr(s, 'is_monotonic_decreasing')  # noqa
         else:
             good = getattr(s, 'is_monotonic_decreasing')
         if strict:
@@ -83,6 +84,7 @@ def is_monotonic(df, items=None, increasing=None, strict=False):
             raise AssertionError
     return df
 
+
 def is_shape(df, shape):
     """
     Asserts that the DataFrame is of a known shape.
@@ -101,7 +103,7 @@ def is_shape(df, shape):
     """
     try:
         check = np.all(np.equal(df.shape, shape) | (np.equal(shape, [-1, -1]) |
-                                                    np.equal(shape, [None, None])))
+                                                    np.equal(shape, [None, None])))  # noqa
         assert check
     except AssertionError as e:
         msg = ("Expected shape: {}\n"
@@ -110,6 +112,7 @@ def is_shape(df, shape):
         raise
     return df
 
+
 def unique_index(df):
     """
     Assert that the index is unique
@@ -151,6 +154,7 @@ def within_set(df, items=None):
             raise AssertionError('Not in set', bad)
     return df
 
+
 def within_range(df, items=None):
     """
     Assert that a DataFrame is within a range.
@@ -172,6 +176,7 @@ def within_range(df, items=None):
             raise AssertionError("Outside range", bad)
     return df
 
+
 def within_n_std(df, n=3):
     """
     Assert that every value is within ``n`` standard
@@ -195,6 +200,7 @@ def within_n_std(df, n=3):
         raise AssertionError(msg)
     return df
 
+
 def has_dtypes(df, items):
     """
     Assert that a DataFrame has ``dtypes``
@@ -241,7 +247,8 @@ def one_to_many(df, unitcol, manycol):
     subset = df[[manycol, unitcol]].drop_duplicates()
     for many in subset[manycol].unique():
         if subset[subset[manycol] == many].shape[0] > 1:
-            msg = "{} in {} has multiple values for {}".format(many, manycol, unitcol)
+            msg = "{} in {} has multiple values for {}".format(many, manycol,
+                                                               unitcol)
             raise AssertionError(msg)
 
     return df
@@ -270,7 +277,34 @@ def is_same_as(df, df_to_compare, **kwargs):
     return df
 
 
+def has_columns(df, columns, **kwargs):
+    """
+    Assert that a pandas dataframe contains given columns
+
+    Parameters
+    ==========
+    :param df: 
+    :param columns: 
+
+    df : pandas DataFrame
+    columns : list of columns
+    **kwargs : dict
+        keyword arguments passed through to panda's ``assert_frame_equal``
+
+    Returns
+    =======
+    :return: df : pandas DataFrame
+    """
+    missing_columns = []
+    for x in columns:
+        if x not in df.columns:
+            missing_columns.append(x)
+
+    if len(missing_columns) > 0:
+        raise AssertionError("DataFrame does not contain "
+                             "required columns: {}".format(missing_columns))
+    return df
+
 __all__ = ['is_monotonic', 'is_same_as', 'is_shape', 'none_missing',
            'unique_index', 'within_n_std', 'within_range', 'within_set',
-           'has_dtypes', 'verify', 'verify_all', 'verify_any']
-
+           'has_dtypes', 'has_columns' 'verify', 'verify_all', 'verify_any']

engarde/decorators.py

@@ -5,6 +5,7 @@
 
 import engarde.checks as ck
 
+
 def none_missing(columns=None):
     """Asserts that no missing values (NaN) are found"""
     def decorate(func):
@@ -38,6 +39,7 @@ def wrapper(*args, **kwargs):
         return wrapper
     return decorate
 
+
 def is_monotonic(items=None, increasing=None, strict=False):
     def decorate(func):
         @wraps(func)
@@ -49,6 +51,7 @@ def wrapper(*args, **kwargs):
         return wrapper
     return decorate
 
+
 def within_set(items):
     """
     Check that DataFrame values are within set.
@@ -102,6 +105,7 @@ def wrapper(*args, **kwargs):
         return wrapper
     return decorate
 
+
 def has_dtypes(items):
     """
     Tests that the dtypes are as specified in items.
@@ -115,6 +119,18 @@ def wrapper(*args, **kwargs):
         return wrapper
     return decorate
 
+def has_columns(columns):
+    """
+    Tests that a dataframe contains required columns
+    """
+    def decorate(func):
+        @wraps(func)
+        def wrapper(*args, **kwargs):
+            result = func(*args, **kwargs)
+            ck.has_columns(result, columns)
+            return result
+        return wrapper
+    return decorate
 
 def one_to_many(unitcol, manycol):
     """ Tests that each value in ``manycol`` only is associated with
@@ -124,7 +140,7 @@ def decorate(func):
         @wraps(func)
         def wrapper(*args, **kwargs):
             result = func(*args, **kwargs)
-            ck.one_to_many(results, unitcol, manycol)
+            ck.one_to_many(result, unitcol, manycol)
             return result
         return wrapper
     return decorate
@@ -136,18 +152,21 @@ def verify(func, *args, **kwargs):
     """
     return _verify(func, None, *args, **kwargs)
 
+
 def verify_all(func, *args, **kwargs):
     """
     Assert that all of `func(*args, **kwargs)` are true.
     """
     return _verify(func, 'all', *args, **kwargs)
 
+
 def verify_any(func, *args, **kwargs):
     """
     Assert that any of `func(*args, **kwargs)` are true.
     """
     return _verify(func, 'any', *args, **kwargs)
 
+
 def _verify(func, _kind, *args, **kwargs):
     d = {None: ck.verify, 'all': ck.verify_all, 'any': ck.verify_any}
     vfunc = d[_kind]
@@ -175,5 +194,5 @@ def wrapper(*args, **kwargs):
 
 __all__ = ['is_monotonic', 'is_same_as', 'is_shape', 'none_missing',
            'unique_index', 'within_range', 'within_set', 'has_dtypes',
-           'verify', 'verify_all', 'verify_any', 'within_n_std']
+           'has_columns', 'verify', 'verify_all', 'verify_any', 'within_n_std']
 

engarde/generic.py

@@ -37,6 +37,7 @@ def verify(df, check, *args, **kwargs):
         raise
     return df
 
+
 def verify_all(df, check, *args, **kwargs):
     """
     Verify that all the entries in ``check(df, *args, **kwargs)``
@@ -51,6 +52,7 @@ def verify_all(df, check, *args, **kwargs):
         raise
     return df
 
+
 def verify_any(df, check, *args, **kwargs):
     """
     Verify that any of the entries in ``check(df, *args, **kwargs)``
@@ -69,9 +71,10 @@ def verify_any(df, check, *args, **kwargs):
 # Error reporting
 # ---------------
 
+
 def bad_locations(df):
     columns = df.columns
-    all_locs = chain.from_iterable(zip(df.index, cycle([col])) for col in columns)
+    all_locs = chain.from_iterable(zip(df.index, cycle([col])) for col in columns)  # noqa
     bad = pd.Series(list(all_locs))[np.asarray(df).ravel(1)]
     msg = bad.values
     return msg

examples/Trains.ipynb

@@ -226,7 +226,6 @@
     {
      "ename": "AssertionError",
      "evalue": "('rational not true for all',        id  choiceid   choice  price1  time1  change1  comfort1  price2  time2  \\\n13      2         3  choice2    2450    121        0         0    2450     93   \n18      2         8  choice2    2975    108        0         0    2450    108   \n27      3         6  choice2    1920    106        0         0    1440     96   \n28      3         7  choice1    1920    106        0         0    1920     96   \n33      4         1  choice2     545    105        1         1     545     85   \n...   ...       ...      ...     ...    ...      ...       ...     ...    ...   \n2899  233        10  choice1    1350    110        0         0    1350     95   \n2900  234         1  choice2    4400     85        1         1    3300     85   \n2907  234         8  choice2    3300     95        1         0    3300     85   \n2914  235         1  choice2    3000     75        2         1    3000     65   \n2916  235         3  choice2    2550     75        1         0    2100     55   \n\n      change2  comfort2  \n13          0         1  \n18          0         1  \n27          0         1  \n28          0         1  \n33          1         1  \n...       ...       ...  \n2899        0         1  \n2900        0         1  \n2907        0         1  \n2914        1         1  \n2916        1         1  \n\n[467 rows x 11 columns])",
-     "output_type": "error",
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mAssertionError\u001b[0m                            Traceback (most recent call last)",
@@ -236,7 +235,8 @@
       "\u001b[0;32m/Users/tom.augspurger/sandbox/engarde/engarde/decorators.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*operation_args, **operation_kwargs)\u001b[0m\n\u001b[1;32m    147\u001b[0m         \u001b[0;32mdef\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0moperation_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0moperation_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    148\u001b[0m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0moperation_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0moperation_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0moperation_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 149\u001b[0;31m             \u001b[0mvfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    150\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    151\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;32m/Users/tom.augspurger/sandbox/engarde/engarde/generic.py\u001b[0m in \u001b[0;36mverify_all\u001b[0;34m(df, check, *args, **kwargs)\u001b[0m\n\u001b[1;32m     40\u001b[0m     \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     41\u001b[0m     \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 42\u001b[0;31m         \u001b[0;32massert\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     43\u001b[0m     \u001b[0;32mexcept\u001b[0m \u001b[0mAssertionError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     44\u001b[0m         \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"{} not true for all\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcheck\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mAssertionError\u001b[0m: ('rational not true for all',        id  choiceid   choice  price1  time1  change1  comfort1  price2  time2  \\\n13      2         3  choice2    2450    121        0         0    2450     93   \n18      2         8  choice2    2975    108        0         0    2450    108   \n27      3         6  choice2    1920    106        0         0    1440     96   \n28      3         7  choice1    1920    106        0         0    1920     96   \n33      4         1  choice2     545    105        1         1     545     85   \n...   ...       ...      ...     ...    ...      ...       ...     ...    ...   \n2899  233        10  choice1    1350    110        0         0    1350     95   \n2900  234         1  choice2    4400     85        1         1    3300     85   \n2907  234         8  choice2    3300     95        1         0    3300     85   \n2914  235         1  choice2    3000     75        2         1    3000     65   \n2916  235         3  choice2    2550     75        1         0    2100     55   \n\n      change2  comfort2  \n13          0         1  \n18          0         1  \n27          0         1  \n28          0         1  \n33          1         1  \n...       ...       ...  \n2899        0         1  \n2900        0         1  \n2907        0         1  \n2914        1         1  \n2916        1         1  \n\n[467 rows x 11 columns])"
-     ]
+     ],
+     "output_type": "error"
     }
    ],
    "source": [
@@ -307,7 +307,7 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 3
+    "version": 3.0
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
@@ -319,4 +319,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}